Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    PHP source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Learn
    -0.07
     يش
    -0.07
     rollers
    -0.06
     Мак
    -0.06
     جمعیت
    -0.06
     Permission
    -0.06
    Mad
    -0.06
     colleague
    -0.06
     Hat
    -0.06
     необхід
    -0.06
    POSITIVE LOGITS
    (false
    0.07
    (asset
    0.06
     Fully
    0.06
    Fully
    0.06
    ={`/
    0.06
    >('
    0.06
    (vals
    0.06
    ILogger
    0.06
    ısından
    0.05
    averse
    0.05
    Act Density 0.028%

    No Known Activations